Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1917 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.3310. Min Act: -0.0000

Data Index: 815199 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1201401 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2937. Min Act: -0.0000

Data Index: 878991 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1400805 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2836. Min Act: -0.0000

Data Index: 40329 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2758. Min Act: -0.0000

Data Index: 187050 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1291206 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2800. Min Act: -0.0000

Data Index: 404516 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1352579 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2762. Min Act: -0.0000

Data Index: 351794 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2811. Min Act: -0.0000

Data Index: 186642 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2538. Min Act: -0.0000

Data Index: 661966 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2725. Min Act: -0.0000

Data Index: 209220 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2786. Min Act: -0.0000

Data Index: 927880 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2773. Min Act: 0.0000

Data Index: 772854 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1608154 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2546. Min Act: -0.0000

Data Index: 35764 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2695. Min Act: -0.0000

Data Index: 418844 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2621. Min Act: -0.0000

Data Index: 891244 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.3310. Min Range: -0.3310

Max Act: 0.2666. Min Act: -0.0000

Data Index: 605250 (C4 (Web Text))

Max Activating Token Index: 201